Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

Silabificador

Silabificador splits a Portuguese word into syllables. It uses hand-crafted rules based on Portuguese phonotactics. It has no runtime dependencies and loads no model.

Features

  • Syllabification for Portuguese, derived from the licit onset inventory and the diphthong/hiatus rules. A short list holds only the words no rule reaches, each with its source.
  • Stress, primary and secondary, read from the orthography that encodes it.
  • Syllable structure, not just strings: onset, glide, nucleus, coda.
  • The output always reconstructs the input. Hyphens, spaces, and apostrophes stay in place and are never dropped.
  • No dependencies.

Installation

pip install silabificador

Silabificador needs Python 3.11 or later. The --pre flag of pip installs the latest alpha.

Usage

from silabificador import syllabify

syllabify("computador")     # ['com', 'pu', 'ta', 'dor']
syllabify("guarda-chuva")   # ['guar', 'da-', 'chu', 'va']

Use analyze for the constituents, or stressed_index for the stress:

from silabificador import analyze, stressed_index

for s in analyze("transportar"):
    print(s.onset, s.nucleus, s.coda, s.stressed)
# tr a ns False
# p  o r  False
# t  a r  True      -> trans.por.TAR

stressed_index("sílaba")   # 0   SÍ.la.ba

A compound keeps a stress on every element. The last element takes the primary stress:

[str(s) for s in analyze("guarda-chuva") if s.secondary]   # ['guar']
[str(s) for s in analyze("guarda-chuva") if s.stressed]    # ['chu']

Documentation

Accuracy

Silabificador is measured against five sources of syllabification:

  • Infopédia (Porto Editora), from the Portuguese Unified Pronunciation Lexicon.
  • Michaelis (Melhoramentos), from the same lexicon.
  • en.wiktionary, from the Kaikki extract of its {{hyph|pt}} templates.
  • pt.wiktionary, from the stress templates ({{paroxítona|ex|cer|to}}) in the Wikimedia dump.
  • The Portal da Língua Portuguesa, from the same lexicon.

The first four are edited by people. The Portal is not. Its Dicionário de divisão silábica says that "as regras de divisão silábica para a criação deste dicionário foram baseadas" on Base XX of the 1990 Orthographic Agreement. Its data agree with that: on every letter shape with two accepted splits, the Portal gives one answer to all of the words. The Portal is therefore scored as its own generated tier and is never gold.

A word can have more than one correct split. Cunha & Cintra accept both a-pto and ap-to; en.wiktionary lists both sub.li.nhar and su.bli.nhar. Each gold entry is a set of accepted splits, and a prediction is correct when it is one of them.

A source sometimes prints a headword with no division: Michaelis gives bacon and arroz-doce whole, and pt.wiktionary gives metodismo. That is no claim about the syllables, so a split is dropped when a piece between two separators holds more than one run of vowels. The rule also drops a few English loans whose syllable holds a silent ⟨e⟩ (soft.ware), and it misses an undivided word whose vowels form one run (voyeur).

tier what it holds accepted match
edge cases cited splits from grammars and dictionaries, tests/edge_cases.json 100.00% 148 / 148
agreement, 4 sources all four human sources give the split 99.97% 10,785 / 10,788
agreement, 3 sources three human sources give the split 99.90% 13,340 / 13,354
agreement, 2 sources two human sources give the split 99.70% 26,180 / 26,260
agreement (gold) the three rows above 99.81% 50,305 / 50,402
Infopédia only one human source 99.30% 59,033 / 59,447
Michaelis only one human source 93.37% 577 / 618
Wiktionary only one human source 98.16% 65,340 / 66,568
conflict human sources share no split; any of them is accepted 99.30% 707 / 712
generated: Portal not gold 99.69% 51,835 / 51,995

All 184,799 scoreable words reconstruct exactly.

Michaelis writes a final unstressed vowel pair such as ⟨ia⟩, ⟨ie⟩ or ⟨ea⟩ as one syllable (gló.ria, sé.rie, náu.sea). Infopédia and the engine write a hiatus (gló.ri.a, sé.ri.e). Cunha & Cintra (p. 63) accept both: final ⟨-ia -ie -io⟩ "são normalmente ditongos crescentes" but "podem, no entanto, ser emitidos com separação dos dois elementos". The edge case glória accepts both splits. A word that only Michaelis holds has only the Michaelis split, so 34 of the 41 Michaelis-only misses come from this difference.

The rules were first tuned on the words where Infopédia and the Portal agree, so the Portal score shows how close the engine is to one rule system, not how correct it is. Where a cited rule and the Portal disagree, the rule wins: the Portal joins every iu (miu.de.za), and the engine follows the human sources (mi.u.de.za).

The edge cases cover the classes where the sources disagree: medial clusters (ap.to and a.pto), prefix seams (sub.li.nhar, a.brup.to and ab.rup.to), hiatus and diphthong (gló.ri.a and gló.ria), the productive prefixes, the hyphenated prefixes of the Agreement (ab-rogar, sub-reino), the hiatus that depends on stress (flu.iu, ci.u.men.to), and words where one source is wrong. Every accepted split names its source.

Stress is measured against a gold the engine cannot see: the lexicon's IPA transcriptions, which mark stress with ˈ. Nothing in the engine reads IPA.

stress accuracy 99.84% 43,756 / 43,826
gold self-check 99.79% 4,709 / 4,719

The self-check gives a reason to trust the gold: on a simple word, a written accent is the stress, by definition of the spelling rules, so the IPA-derived answer must agree with it, and it does.

To reproduce the numbers and see every remaining failure bucketed by cause, run the commands below. The first run downloads the two Wiktionary dumps (about 130 MB) into ~/.cache/silabificador.

pip install -e ".[benchmark]"
python -m benchmark.report

Silabificador is part of the TigreGotico Portuguese phonetics toolchain, alongside:

Development

pip install -e ".[test]"
python -m pytest tests

The suite runs offline. tests/test_accuracy_regression.py scores a fixed sample of the gold in tests/gold_sample.json, and the full scoreboard comes from python -m benchmark.report. Do not edit docs/accuracy.md by hand.

License

MIT License

Metadata

Release files for silabificador 2.1.13a1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for silabificador 2.1.13a1
File Size Uploaded Provenance Actions
silabificador-2.1.13a1.tar.gz 48.7 kB Without provenance Details for silabificador-2.1.13a1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for silabificador 2.1.13a1
File Interpreter ABI Platform Actions
silabificador-2.1.13a1-py3-none-any.whl Python 3 none any Details for silabificador-2.1.13a1-py3-none-any.whl

Total release size: 82.7 kB

Release files / silabificador-2.1.13a1.tar.gz

Download URL silabificador-2.1.13a1.tar.gz
Size 48.7 kB
Tags Source
SHA-256 checksum
How to use checksums
5bbe920ce3d70fc91f119de1404bdc6a513dd42d267dde20982a1f69ec6bde4f
BLAKE2b-256 checksum
How to use checksums
89376ddf397c6057a9ecd225e3720ffef19d49b802cfef27c2d238a6570fb35e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.16

Release files / silabificador-2.1.13a1-py3-none-any.whl

Download URL silabificador-2.1.13a1-py3-none-any.whl
Size 34.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
db0d72f88ed53e0d3760f7465c3d9f6b7439a193014362e60655ea07ad794db8
BLAKE2b-256 checksum
How to use checksums
5f2a9f2b3ca3e8f16518effff58915e9d0d51115956b05a524fd7842e8902176
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.16

Security for silabificador 2.1.13a1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release
Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page